Optimization of Steaming Conditions for Bellflower Root (Platycodon grandiflorus) Using K-Means Clustering-Based Morphological Grading System

Abstract

Bellflower roots were categorized into three clusters (class 0, class 1, and class 2) using K-means clustering based on their morphological factors: length (282.8 ± 29.53, 138.75 ± 26.8, and 209.89 ± 20.49 mm), thickness (16.25 ± 2.82, 16.77 ± 3.35, and 16.52 ± 3.05 mm), and body shape coefficient (5.80 ± 1.15, 12.73 ± 4.82, and 7.95 ± 1.71). Internal void formation, a key quality factor for bellflower root, was analyzed under pre-steaming conditions, identifying temperatures between 20 and 25 °C as optimal for storage. Within the clustered class, steaming for a prolonged duration increased the formation of internal voids and caused a decrease in normal stress values, total dissolved solids (TDS), and pectin content. Class 0, with larger and thicker roots, exhibited higher internal voids (57% void rate) due to uneven heat distribution and incomplete starch gelatinization. Class 2 roots demonstrated better structural integrity, with a void rate of 26% and a stress value of 48 kN/m2. These findings highlight the importance of morphological classification and optimal storage temperatures to improve the quality of steamed bellflower roots.